End of training

README.md

@@ -2,7 +2,10 @@
 license: apache-2.0
 base_model: albert-base-v2
 tags:
+- question-answering
 - generated_from_trainer
+datasets:
+- squad
 model-index:
 - name: out
   results: []
@@ -13,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # out
 
-This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the None dataset.
+This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the squad dataset.
 
 ## Model description
 

all_results.json

@@ -1,11 +1,11 @@
 {
-    "epoch": 10.0,
+    "epoch": 20.0,
     "eval_samples": 3000,
-    "exact_match": 69.53333333333333,
-    "f1": 79.31930468455819,
-    "train_loss": 0.41871513204371674,
-    "train_runtime": 197.2832,
+    "exact_match": 69.36666666666666,
+    "f1": 79.08588444044621,
+    "train_loss": 0.22334851051898713,
+    "train_runtime": 394.6502,
     "train_samples": 3000,
-    "train_samples_per_second": 152.066,
+    "train_samples_per_second": 152.033,
     "train_steps_per_second": 2.382
 }

args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd0965d3f563470f46319346d7038ec4e65efd9c85c61b754fea0b3171d83795
+oid sha256:8ebb76576d393772ce9acaf130f6a516d00cca9735839842c18cad289f875a8f
 size 5652

eval_nbest_predictions.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0469941bf7a263ccfea4d74ea5f96411516ccfeaffbcb9f28ddedf5e7a4dd66
-size 13456510
+oid sha256:43e54f478041686203905682d07dcebcef703f5d5cc43b46912c0f93f9219735
+size 13496195

eval_results.json

@@ -1,6 +1,6 @@
 {
-    "epoch": 10.0,
+    "epoch": 20.0,
     "eval_samples": 3000,
-    "exact_match": 69.53333333333333,
-    "f1": 79.31930468455819
+    "exact_match": 69.36666666666666,
+    "f1": 79.08588444044621
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 10.0,
-    "train_loss": 0.41871513204371674,
-    "train_runtime": 197.2832,
+    "epoch": 20.0,
+    "train_loss": 0.22334851051898713,
+    "train_runtime": 394.6502,
     "train_samples": 3000,
-    "train_samples_per_second": 152.066,
+    "train_samples_per_second": 152.033,
     "train_steps_per_second": 2.382
 }

trainer_state.json

@@ -1,28 +1,34 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.0,
+  "epoch": 20.0,
   "eval_steps": 500,
-  "global_step": 470,
+  "global_step": 940,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 10.0,
-      "step": 470,
-      "total_flos": 496885570560000.0,
-      "train_loss": 0.41871513204371674,
-      "train_runtime": 197.2832,
-      "train_samples_per_second": 152.066,
+      "epoch": 10.64,
+      "learning_rate": 2.340425531914894e-05,
+      "loss": 0.4117,
+      "step": 500
+    },
+    {
+      "epoch": 20.0,
+      "step": 940,
+      "total_flos": 993771141120000.0,
+      "train_loss": 0.22334851051898713,
+      "train_runtime": 394.6502,
+      "train_samples_per_second": 152.033,
       "train_steps_per_second": 2.382
     }
   ],
   "logging_steps": 500,
-  "max_steps": 470,
-  "num_train_epochs": 10,
+  "max_steps": 940,
+  "num_train_epochs": 20,
   "save_steps": 500,
-  "total_flos": 496885570560000.0,
+  "total_flos": 993771141120000.0,
   "trial_name": null,
   "trial_params": null
 }